© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 63688
    Prev
    Next
    INDEX
    Explanations

    baryonic, neutron, spin, charmonium

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ÏĥÏį
    -0.08
    endent
    -0.08
     cera
    -0.07
     ÑģмÑĭ
    -0.07
     Ero
    -0.07
     TokenType
    -0.07
    olutions
    -0.07
    æĬĺ
    -0.07
    fahr
    -0.07
    hots
    -0.07
    POSITIVE LOGITS
    spin
    0.07
    éģįéĩİ
    0.07
    èµ·åIJį
    0.07
    çŃī大åŀĭ
    0.06
    æłĭæ¢ģ
    0.06
    vecs
    0.06
    неÑģли
    0.06
     spin
    0.06
    ấm
    0.06
     grav
    0.06
    Activations Density 0.004%

    No Known Activations